Video surveillance systems are commonly employed to monitor activities and ensure the safety and security of various environments. Anomaly detection in these systems is challenging due to the rarity and high variability of abnormal events. Integrating anomaly detection enables the identification of atypical or suspicious activities. This paper proposes a novel approach for video anomaly detection based on ensemble learning in a weakly supervised setting. The method consists of a two-stage framework. In the first stage, spatiotemporal features are extracted from video data using 3D deep networks, followed by a multiscale attention module to enhance feature representation. Anomalous events are then identified by analysing discrepancies in probabilistic distributions, incorporating multi-instance learning with a novel term in the loss function. In the second stage, the detection process is refined through ensemble learning strategies to optimise overall performance. The effectiveness of the proposed framework is demonstrated through extensive experiments on five benchmark datasets: UCF-Crime, XD-Violence, ShanghaiTech, CUHK Avenue, and UCSD Ped2. The method achieves frame-level AUC scores of 97.89% on ShanghaiTech, 95.97% on CUHK Avenue, 97.38% on UCSD Ped2, 94.02 on XD-Violence, and 80.86% on UCF-Crime, showing competitive performance and highlighting the potential of ensemble-based weakly supervised methods for video anomaly detection.

Keywords